The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models. Is intended as a way to fight back against AI companies that use artists’ work to train their models without the creator’s permission.
ARTICLE - Technology Review
ARTICLE - Mashable
ARTICLE - Gizmodo
The researchers tested the attack on Stable Diffusion’s latest models and on an AI model they trained themselves from scratch. When they fed Stable Diffusion just 50 poisoned images of dogs and then prompted it to create images of dogs itself, the output started looking weird—creatures with too many limbs and cartoonish faces. With 300 poisoned samples, an attacker can manipulate Stable Diffusion to generate images of dogs to look like cats.
Wasn’t there already a tool like this called Glaze?
This is pretty much Glaze 2. It just intentionally poisons the data set with specific targets so model is more fucked. Originally it was just noise being put in and ultimately a image that had been glazed would just get tossed. With this, the image will actually fuck up the resulting model of there is enough poisoned data included.
Probably, I’m not an expert obviously.